برنامه ریزی تمدید دوره آموزش برای پاسخگویی به تقاضای بازار با استفاده از تکنیک های داده کاوی - به عنوان مثال دانشگاه تکنولوژی Chinkuo در تایوان
|کد مقاله||سال انتشار||مقاله انگلیسی||ترجمه فارسی||تعداد کلمات|
|22103||2008||7 صفحه PDF||سفارش دهید||محاسبه نشده|
Publisher : Elsevier - Science Direct (الزویر - ساینس دایرکت)
Journal : Expert Systems with Applications, Volume 34, Issue 1, January 2008, Pages 596–602
This study used data mining techniques to analyze the course preferences and course completion rates of enrollees in extension education courses at a university in Taiwan. First, extension courses were classified into five broad groups. Records of enrollees in extension courses from 2000-5 were then analyzed by three data mining algorithms: Decision Tree, Link Analysis, and Decision Forest. Decision tree was used to find enrollee course preferences, Link Analysis found the correlation between course category and enrollee profession, and Decision Forest found the probability of enrollees completing preferred courses. Results will be used as a reference for curriculum development in the extension program.
In the last two decades, a revolution in education has followed on the heels of economic growth and political reform. The number of institutions of higher education has increased steadily, and vocational junior colleges offering two year degrees are being phased out, upgrading to universities/institutes of technology offering 4 year degree programs. To meet the demand for higher education, the number of institutions of higher education in Taiwan is expected to increase to 155 over the next twenty years, up from the current 30 (Department of Higher Education, 2005). Education has gone from being the province of elites to a commodity accessible to anyone. As the number of colleges has increased, colleges and universities have found themselves facing stiff competition for students. As a result, many colleges and universities have established Continuing/Extension Education Centers to provide accredited and non-accredited courses as well as short- and medium-term vocational training for adults, both in and out of the employment pool. These institutions take as a foundational principle that successful long-term management of extension education must be focused on satisfying the needs of the community, local industry, and local professional development. The purpose of this research was to use data mining techniques to uncover the preferences and future choices of continuing education students of an Extension Education Center at a university in Taiwan. This data would then be used to better target curriculum on student needs. Decision Tree Algorithms, Link Analysis Algorithms, and Decision Forest Algorithms developed from the theory of Data mining were used in this research. Data consisted of the student records of enrollees in courses in the 5 academic years from 2000 to 2005 planned by the Extension Education Center of Chienkuo Technology University (hereinafter CTU). Results of the research included (1) course preferences of enrollees; (2) the relationship between course categories offered and enrollee profession; (3) the relationship between course preferences, enrollee profession and the probability of course completion. These results will be used as a reference in future curriculum development at the Extension Education Center of CTU.
نتیجه گیری انگلیسی
In this study, data mining is used to look for correlations between the preferred course category and enrollee profession, among enrollees in extension courses at CTU over five academic years between 2000 and 2005. First, Decision Tree was used to build up a structure tree relation, which was used to find the preferred courses. Next, Link Analysis was used to find the correlation between course category and enrollee profession. Finally, Decision Forest found the preferred courses of enrollees from different sectors, along with the probability of course completion for enrollees by sector. Based on the results of applied three algorithms in this study, the Extension Education Center at CTU can plan future courses based on the needs of different enrollee professions. This study also shows that data mining may have great promise as a reference for curriculum development and marketing in any field of higher education, not just extension education. Future research can follow many different directions. Once curriculum has been adjusted in the directions suggested by the results of data mining, studies should be performed to determine whether recruiting has risen as a result of the targeted curriculum. Data from other universities in the local area may also be investigated to better understand the needs of local students and local industry. Further, additional data mining techniques should be investigated for their applicability to this type of research.